Host code debugging using CUDA debugger : Nsight for VSE 4.0

Hi All,

I am trying to debug host code using the CUDA debugger but it doesnt seem to stop at any of the break points set in the host code . However it does stop at a break point set in my kernel (device code),

Does nSight for VSE 4.0 support host code debugging along with device code debugging?

My setup is as follows:

  1. OS : Windows 8.1
  2. Visual Studio Professional 2010 with SP1
  3. nSight for VSE 4.0
  4. Driver version 340.52 - Recommended version by nvidia is 332.44 or newer.
  5. Cuda Toolkit 6.5
  6. Headless debugging set using GT640. Im using another card for the monitor. CUDA_VISIBLE_DEVICE is set
  7. Debugging mode : Local Debugging

Any inputs regarding this issues is most welcome

Referring to the documentation:

http://docs.nvidia.com/gameworks/index.html#developertools/desktop/launch_cuda_debugger.htm%3FTocPath%3DDeveloper%20Tools|Desktop%20Developer%20Tools|NVIDIA%20Nsight%20Visual%20Studio%20Edition|NVIDIA%20Nsight%20Visual%20Studio%20Edition%204.1|CUDA%20Debugger|How%20To|_____2

"NOTE: You cannot debug CUDA code in a target process while simultaneously debugging the x86 code of the same process.

Use a separate Visual Studio instance to debug the host portion of a target application. If you wish to debug the host portion of your CUDA application while the CUDA Debugger is attached, you must attach using a different Visual Studio instance. Attaching the same instance of Visual Studio to debug both the host portion and the device portion of a target application will cause the debuggers to conflict. The result is that the target application and the CUDA Debugger hang while being blocked by operations of the native debugger.
"